Abstract
Smartwatches and smartphones are extensively used in human activity recognition, particularly for step counting and daily sports applications, thanks to the motion sensors integrated into these devices. Machine learning algorithms are often utilized to process sensor data and classify the activities. There are many studies that explore the use of traditional classification algorithms in activity recognition, however, recently, deep learning approaches are also receiving attention. In this paper, we use a dataset that particularly consists of smoking-related activities and explores the recognition performance of three deep learning architectures, namely Long-Short Term Memory (LSTM)}, Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN). We evaluate their performances according to different hyperparameters, different sensor types and device types. The results show that the performance of LSTM is much higher than that of CNN and RNN. Moreover, the use of magnetometer and gyroscope together with accelerometer data improves the performance. Use of data from smartphone sensors also enhances the performance results and the final accuracy with the best parameter combinations is observed to be 98%.
Highlights
WEARABLE DEVICES such as smartwatches and smart glasses, that are integrated with a variety of sensors, are commonly used in human activity recognition studies [1,2]
We investigate the use of different deep learning algorithms, namely Long-Short Term Memory (LSTM), Recurrent Neural Networks (RNN) and Convolutional Neural Networks (CNN) on activity recognition with mobile and wearable devices
In this paper, we studied the problem of sensor-based smoking recognition using three deep learning architectures (LSTM, RNN and CNN) with different hyperparameter settings
Summary
WEARABLE DEVICES such as smartwatches and smart glasses, that are integrated with a variety of sensors, are commonly used in human activity recognition studies [1,2]. Motion sensors available on these devices make it easy to collect and analyze data for sports and well-being applications. In some studies [2], classification of general activities is targeted for monitoring the activity levels, for example, for fitness purposes, while in some others, more specific activities are monitored, such as fall detection [3]. Activities related to wrist and hand movements can be recognized with smartwatches. Smoking is one of the activities that users may be interested in tracking. For smoking cessation programs, it may be practical to automatically track the number of cigarettes smoked instead of self-reporting which puts a burden on the user [4]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callMore From: Balkan Journal of Electrical and Computer Engineering
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
